#subliminal-learning

1 articles

01 ·Inference & Serving·★ MEMBER·PAPER·9 min read Paper Explained: Post-Training Leaves Behavioral Shadows on Unrelated Decisions — capability transfer through one unrelated word Ask a code-tuned model to pick between 'jacket' and 'tie' a few thousand times, and another model can inherit part of its coding gain. A from-scratch walkthrough of Active Taskless Distillation (ATD): the math, the controls, and the limits.